Clustering via fuzzy one-class quadratic surface support vector machine

This paper proposes a soft clustering algorithm based on a fuzzy one-class kernel-free quadratic surface support vector machine model. One main advantage of our new model is that it directly uses a quadratic function for clustering instead of the kernel function. Thus, we can avoid the difficult task of finding a proper kernel function and corresponding parameters. Besides, for handling data sets with a large amount of outliers and noise, we introduce the Fisher discriminant analysis to consider minimizing the within-class scatter. Our experimental results on some artificial and real-world data sets demonstrate that the proposed algorithm outperforms Bicego's benchmark algorithm in terms of the clustering accuracy and efficiency. Moreover, this proposed algorithm is also shown to be very competitive with several state-of-the-art clustering methods.